Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas, in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eternity
    -0.75
    lust
    -0.75
    jad
    -0.70
    =#
    -0.66
    wid
    -0.65
    stro
    -0.64
    imei
    -0.63
    Override
    -0.62
    hedon
    -0.62
    stroke
    -0.60
    POSITIVE LOGITS
     chaired
    1.19
     which
    1.08
     headquartered
    1.05
     aka
    0.91
     housed
    0.87
     convened
    0.86
     comprising
    0.85
     founded
    0.84
     wherein
    0.84
     whose
    0.83
    Act Density 0.162%

    No Known Activations